fix: per-dimension alert descriptions when multiple dimensions fail

integration_tests/tests/adapter_query_runner.py

@@ -52,9 +52,14 @@ def _serialize_value(val: Any) -> Any:
     * Everything else is returned unchanged.
     """
     if isinstance(val, Decimal):
-        # Match the Jinja macro: normalize, then int or float
+        # Match the Jinja macro: normalize, then int or float.
+        # Note: for special values (Infinity, NaN), as_tuple().exponent is a
+        # string ('F' or 'n'), not an int — convert those directly to float.
         normalized = val.normalize()
-        if normalized.as_tuple().exponent >= 0:
+        exponent = normalized.as_tuple().exponent
+        if isinstance(exponent, str):
+            return float(normalized)
+        if exponent >= 0:
             return int(normalized)
         return float(normalized)
     if isinstance(val, (datetime, date, time)):

integration_tests/tests/test_dimension_anomalies.py

@@ -315,3 +315,83 @@ def test_anomaly_in_detection_period(
     )
 
     assert test_result["status"] == expected_status
+
+
+def test_dimension_anomalies_alert_description_few_failures(
+    test_id: str, dbt_project: DbtProject
+):
+    """When ≤5 dimension values fail, description shows each one's anomaly details."""
+    utc_today = datetime.utcnow().date()
+    test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
+
+    # 3 dimension values all spike on test_date (training: 1/day, test: 10/day)
+    anomalous_dimensions = ["Batman", "Superman", "Spiderman"]
+
+    data: List[Dict[str, Any]] = [
+        {TIMESTAMP_COLUMN: test_date.strftime(DATE_FORMAT), "superhero": hero}
+        for hero in anomalous_dimensions
+        for _ in range(10)
+    ]
+    data += [
+        {TIMESTAMP_COLUMN: cur_date.strftime(DATE_FORMAT), "superhero": hero}
+        for cur_date in training_dates
+        for hero in anomalous_dimensions
+    ]
+
+    test_args = {
+        "timestamp_column": TIMESTAMP_COLUMN,
+        "dimensions": ["superhero"],
+        "sensitivity": 2,
+    }
+    test_result = dbt_project.test(test_id, DBT_TEST_NAME, test_args, data=data)
+    assert test_result["status"] == "fail"
+
+    description = test_result["test_results_description"]
+    # Each failing dimension value should appear in the description
+    for hero in anomalous_dimensions:
+        assert hero in description, f"Expected '{hero}' in description: {description}"
+    # Should NOT show the high-volume summary message
+    assert "dimension values are anomalous" not in description
+
+
+def test_dimension_anomalies_alert_description_many_failures(
+    test_id: str, dbt_project: DbtProject
+):
+    """When >5 dimension values fail, description shows a count summary."""
+    utc_today = datetime.utcnow().date()
+    test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
+
+    # 6 dimension values all spike on test_date (>5 threshold)
+    anomalous_dimensions = [
+        "Batman",
+        "Superman",
+        "Spiderman",
+        "IronMan",
+        "Thor",
+        "Hulk",
+    ]
+
+    data: List[Dict[str, Any]] = [
+        {TIMESTAMP_COLUMN: test_date.strftime(DATE_FORMAT), "superhero": hero}
+        for hero in anomalous_dimensions
+        for _ in range(10)
+    ]
+    data += [
+        {TIMESTAMP_COLUMN: cur_date.strftime(DATE_FORMAT), "superhero": hero}
+        for cur_date in training_dates
+        for hero in anomalous_dimensions
+    ]
+
+    test_args = {
+        "timestamp_column": TIMESTAMP_COLUMN,
+        "dimensions": ["superhero"],
+        "sensitivity": 2,
+    }
+    test_result = dbt_project.test(test_id, DBT_TEST_NAME, test_args, data=data)
+    assert test_result["status"] == "fail"
+
+    description = test_result["test_results_description"]
+    # Should show the count summary for many failures
+    assert "dimension values are anomalous" in description, (
+        f"Expected summary message in description: {description}"
+    )

macros/edr/data_monitoring/anomaly_detection/store_anomaly_test_results.sql

@@ -74,23 +74,37 @@
           and upper(column_name) = upper({{ elementary.const_as_string(column_name) }})
         {%- endif %}
     {%- endset -%}
-    {% set test_results_description %}
-      {% if rows_with_score %}
-          {{ elementary.insensitive_get_dict_value(rows_with_score[-1], 'anomaly_description') }}
-      {% else %}
-          Not enough data to calculate anomaly score.
-      {% endif %}
-    {% endset %}
     {% set failures = namespace(data=0) %}
     {% set filtered_anomaly_scores_rows = [] %}
+    {% set anomalous_rows = [] %}
     {% for row in anomaly_scores_rows %}
         {% if row.anomaly_score is not none %}
             {% do filtered_anomaly_scores_rows.append(row) %}
             {% if row.is_anomalous %}
                 {% set failures.data = failures.data + 1 %}
+                {% do anomalous_rows.append(row) %}
             {% endif %}
         {% endif %}
     {% endfor %}
+    {%- set max_dimension_alerts = 5 -%}
+    {% set test_results_description %}
+      {%- if rows_with_score -%}
+        {%- set sample_row = rows_with_score[-1] -%}
+        {%- set row_dimension = elementary.insensitive_get_dict_value(sample_row, "dimension") -%}
+        {%- if row_dimension is not none and anomalous_rows | length > 0 -%}
+          {%- if anomalous_rows | length > max_dimension_alerts -%}
+            {%- set remaining = (anomalous_rows | length) - max_dimension_alerts -%}
+            {{ anomalous_rows | length }} dimension values are anomalous. Showing first {{ max_dimension_alerts }}: {% for row in anomalous_rows[:max_dimension_alerts] %}{{ elementary.insensitive_get_dict_value(row, "dimension_value") }}{% if not loop.last %}, {% endif %}{% endfor %}, and {{ remaining }} more.
+          {%- else -%}
+            {% for row in anomalous_rows %}{{ elementary.insensitive_get_dict_value(row, "anomaly_description") }}{% if not loop.last %} | {% endif %}{% endfor %}
+          {%- endif -%}
+        {%- else -%}
+          {{ elementary.insensitive_get_dict_value(rows_with_score[-1], "anomaly_description") }}
+        {%- endif -%}
+      {%- else -%}
+        Not enough data to calculate anomaly score.
+      {%- endif -%}
+    {% endset %}
     {% set test_result_dict = {
         "id": elementary.insensitive_get_dict_value(latest_row, "id"),
         "data_issue_id": elementary.insensitive_get_dict_value(